Linear Categorical Marginal Modeling of solicited symptoms in vaccine clinical trials

Analysis of the occurrence of adverse events, and in particular of solicited symptoms, following vaccination is often needed for the safety and benefit-risk evaluation of any candidate vaccine, and typically involves taking repeated measurements. In this article, it is shown that Linear Categorical Marginal Models (LCMMs) are well suited to take into account the dependencies in the data arising from the repeated measurements and provide detailed and useful information for comparing safety profiles of different products while remaining relatively easy to interpret. LCMMs are presented and applied to a Phase III clinical trial of a candidate meningococcal pediatric vaccine